论文笔记 Very Deep Convolutional Networks for Large-Scale Visual Recognition - ICLR 2014
VGG
Very Deep Convolutional Networks for Large-Scale Visual Recognition
Karen Simonyan and Andrew Zisserman
ICLR, 2014 (PDF) (Citations 73354)
Contribution
- 通过堆叠多个
3x3
的卷积核来替代大尺度卷积核(减少所需参数,两个3x3
的卷积核和一个5x5
的卷积核具有相同的感受野,三个3x3
的卷积核和一个7x7
的卷积核具有相同的感受野)。 AlexNet
提出的LRN
实际用处不大(可以使用BN
)。
Details
- ILSVRC’14 2nd in classification, 1st in localization
- Use VGG16 or VGG19 (VGG19 only slightly better, more memory)
- Use ensembles for best results
- FC7 features generalize well to other tasks
参数计算(VGG16, not counting biases)
Layer | input size | memory | params |
---|---|---|---|
INPUT | [224×224×3] | 224×224×3=150K | 0 |
CONV3-64 | [224×224×64] | 224×224×64=3.2M | (3×3×3)×64=1,728 |
CONV3-64 | [224×224×64] | 224×224×64=3.2M | (3×3×64)×64=36,864 |
POOL2 | [112×112×64] | 112×112×64=800K | 0 |
CONV3-128 | [112×112×128] | 112×112×128=1.6M | (3×3×64)×128=73,728 |
CONV3-128 | [112×112×128] | 112×112×128=1.6M | (3×3×128)×128=147,456 |
POOL2 | [56×56×128] | 56×56×128=400K | 0 |
CONV3-256 | [56×56×256] | 56×56×256=800K | (3×3×128)×256=294,912 |
CONV3-256 | [56×56×256] | 56×56×256=800K | (3×3×256)×256=589,824 |
CONV3-256 | [56×56×256] | 56×56×256=800K | (3×3×256)×256=589,824 |
POOL2 | [28×28×256] | 28×28×256=200K | 0 |
CONV3-512 | [28×28×512] | 28×28×512=400K | (3×3×256)×512=1,179,648 |
CONV3-512 | [28×28×512] | 28×28×512=400K | (3×3×512)×512=2,359,296 |
CONV3-512 | [28×28×512] | 28×28×512=400K | (3×3×512)×512=2,359,296 |
POOL2 | [14×14×512] | 14×14×512=100K | 0 |
CONV3-512 | [14×14×512] | 14×14×512=100K | (3×3×512)×512=2,359,296 |
CONV3-512 | [14×14×512] | 14×14×512=100K | (3×3×512)×512=2,359,296 |
CONV3-512 | [14×14×512] | 14×14×512=100K | (3×3×512)×512=2,359,296 |
POOL2 | [7×7×512] | 7×7×512=25K | 0 |
D | [1×1×4096] | 4096 | 7×7×512×4096=102,760,448 |
FC | [1×1×4096] | 4096 | 4096×4096 = 16,777,216 |
FC | [1×1×1000] | 1000 | 4096×1000 = 4,096,000 |
TOTAL memory
: 24M × 4 bytes ≈ 96MB / image (for a forward pass)
TOTAL params
: 138M parameters
Notes:
- Most memory is in early CONV
- Most params are in late FC
References
- cs231n
论文笔记 Very Deep Convolutional Networks for Large-Scale Visual Recognition - ICLR 2014相关推荐
- VGGNet论文翻译-Very Deep Convolutional Networks for Large-Scale Image Recognition
Very Deep Convolutional Networks for Large-Scale Image Recognition Karen Simonyan[‡] & Andrew Zi ...
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition 一般视觉识别的深度卷积刺激特征
DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition 一般视觉识别的深度卷积刺激特征 Abstra ...
- 论文阅读——Quantizing deep convolutional networks for efficient inference: A whitepaper
Quantizing deep convolutional networks for efficient inference: A whitepaper Abstract 本文针对如何对卷积神经网络的 ...
- 关于GCN的论文笔记--End-to-end Structure-Aware Convolutional Networks for Knowledge Base Completion
用于知识图谱完成的端到端结构感知卷积网络 论文题目 End-to-end Structure-Aware Convolutional Networks for Knowledge Base Compl ...
- 论文阅读-VERY DEEP CONVOLUTIONAL NETWORKS FOR LARGE-SCALE IMAGE RECOGNITION
作者: Karen Simonyan et al. 日期: 2015 类型: conference article 来源: ICLR 评价: veyr deep networks 论文链接: http ...
- 论文笔记《Fully Convolutional Networks for Semantic Segmentation》
[论文信息] <Fully Convolutional Networks for Semantic Segmentation> CVPR 2015 best paper key word: ...
- 【深度学习论文笔记】DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
时间:2014/7/29 10:00 论文题目:DeCAF: A Deep Convolutional Activation Featurefor Generic Visual Recognit ...
- 【论文笔记】Region-based Convolutional Networks for Accurate Object Detection and Segmentation
<Region-based Convolutional Networks for Accurate Object Detection and Segmentation>是将卷积神经网络应用 ...
- DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
2018.4.22星期日 [1]Donahue J, Jia Y, Vinyals O, et al. DeCAF: A Deep ConvolutionalActivation Feature fo ...
最新文章
- 表单高级应用和语义化
- 2021 IEEE热门AI话题盘点:模仿生物大脑打造神经网络、GPT3“不当言论”惹关注…...
- IOS开发基础知识--碎片13
- c语言程序设计的一般错误的是,《C语言程序设计》第十章 程序常见错误分析.pdf...
- 【java】JVM中Perm区持续上涨问题
- observable java_java源码阅读Observable(观察者模式)
- 手把手教你如何建立自己的Linux系统
- 深入浅出Mysql 读书笔记
- java计算机毕业设计工会会员管理系统MyBatis+系统+LW文档+源码+调试部署
- 网站怎么移动适配?这些小技巧你必须要会
- 【寻找最佳小程序】13期:心算练习——寓教于乐,练就小朋友强大的算术能力...
- VB.NET学习笔记:使用Random类生成随机数(不重复、数字、字母)
- 搜狗浏览器个人数据丢失解决方案
- PySpark基础入门(3):RDD持久化
- 大数据+物联网智能交通系统
- 次元服务器的位置,暮色次元服务器介绍
- Flutter 状态管理之Bloc下
- 静态方法与非静态方法区别
- 有苦有乐的算法 --- 随机快排
- 写给朝九晚五的上班族的一封信(转)